This project predicts the likelihood of heart disease using a machine learning model. The notebook includes data preprocessing, exploratory data analysis (EDA), and model training with 80% accuracy .
Heart disease is a major cause of death worldwide, and predicting its occurrence can save lives by enabling timely intervention. This project uses machine learning techniques to classify individuals based on their likelihood of having heart disease.
- Data Preprocessing: Handles missing values and scales the dataset.
- Exploratory Data Analysis (EDA): Visualizes relationships between features and the target variable.
- Model Training: Implements machine learning models such as Logistic Regression, Decision Trees, or others.
- Evaluation: Includes metrics like accuracy, precision, recall, and F1-score to assess model performance.
- Clone this repository:
git clone https://github.com/B1tW1z/heart-disease-prediction.git cd heart-prediction - Ensure you have Python installed along with Jupyter Notebook and the required libraries.
- Place the dataset CSV file in the same directory as the notebook.
- Open the Jupyter Notebook:
jupyter notebook heart_prediction.ipynb
- Run the cells in sequence to execute the data preprocessing, EDA, model training, and evaluation steps.
The project outputs:
- Data visualizations highlighting key patterns in the dataset.
- KNN , Logistic Regression and Random Forest used to train
- Performance metrics of the trained machine learning model.
Contributions are welcome! Please fork the repository and submit a pull request with your changes.